swcr-register
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external repositories, including source code and README files. Malicious instructions embedded in these files could attempt to influence the agent's behavior when it displays or processes the generated summaries.
- Ingestion points: Remote Git repositories (via
git clone) and local file paths provided by the user. - Boundary markers: The skill does not use explicit delimiters or instructions to ignore embedded commands within the ingested content when presenting extracted summaries to the agent.
- Capability inventory: The skill has capabilities for network access (
git clone), file system read/write access, and document generation. - Sanitization: There is no evidence of sanitization or filtering applied to the text extracted from the codebase or documentation files before it is processed or displayed.
- [EXTERNAL_DOWNLOADS]: The workflow involves cloning external codebases from user-provided Git URLs. While necessary for the skill's purpose, this involves fetching content from remote servers.
- [COMMAND_EXECUTION]: The skill executes shell commands to clone repositories and runs Python scripts to perform document generation and analysis tasks.
Audit Metadata